INDEX

Explanations

phrases that include prepositions and conjunctions indicating relationships or connections

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÏĮÏģ

-0.16

imal

-0.15

 Lloyd

-0.14

ermann

-0.14

alm

-0.14

åĦ¿

-0.14

exp

-0.14

.AspNet

-0.14

oft

-0.14

åĦĢ

-0.14

POSITIVE LOGITS

ÑĤÐ°Ð¿

0.15

ixo

0.14

nat

0.14

abama

0.13

 checkboxes

0.13

_ts

0.13

nat

0.13

icon

0.13

 æ¬

0.13

Ð¡Ðł

0.13

Activations Density 0.240%

phrases that include prepositions and conjunctions indicating relationships or connections

No Comments

No Known Activations